© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111225
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [âĢ¦
    -0.29
    [âĢ¦]
    -0.27
    angu
    -0.26
    éĽĢ
    -0.25
     slowing
    -0.25
    IRA
    -0.25
    ILLA
    -0.25
    itioner
    -0.24
    ôme
    -0.24
    èĦ¸
    -0.24
    POSITIVE LOGITS
    ä¸ĢåĪĢ
    0.27
     participates
    0.25
    atti
    0.25
    amu
    0.25
    ä¸ĢåĪ»
    0.24
    an
    0.24
    +x
    0.23
    ализ
    0.23
    def
    0.23
    åľ¨çİ°åľº
    0.23
    Activations Density 0.010%

    No Known Activations